Bedrock AgentCore (AWS)

https://aws.amazon.com/bedrock/agentcore/

AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).

Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 38 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T2
Created
2025-07 vendor fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
Funding
Amazon / AWS (parent) vendor fix
Freshness
2026-10-26 fix
Layer
agent-infra repo fix
Licensing
commercial vendor fix
Deployment locus
cloud vendor fix
Platform vs product
platform vendor fix

When to use

Optimised for: framework-agnostic AWS-managed agent runtime

Anti-fit: AWS-centric; preview-tier maturity; pricing complexity

Pros & cons

Pros

Only major-cloud-managed framework-agnostic agent runtime; OTel observability is first-class; chooses Mem0 as canonical memory provider.

Cons

Preview; AWS-only; pricing complexity inherited from AWS; lots of moving parts to learn (Runtime + Identity + Memory + ...).

Claims & capabilities

AWS-managed runtime preview Jul 2025; framework-agnostic; integrates with Strands Agents, Mem0 as memory provider.

Technical surface

API surface
AWS SDK (Python, JS, Java); Bedrock API
Backend storage
AWS-managed (DynamoDB, S3, OpenSearch under the hood)
Deployment
Managed-only — AWS-hosted (Runtime, Gateway, Memory, Identity, Browser, Code Interpreter, Observability)
Embedding model
not applicable — not a memory product
Multi-tenancy
AWS account isolation
MCP
yes — Gateway exposes APIs/Lambdas as MCP servers; Runtime hosts MCP-compatible tools; Agent Registry publishes MCP servers
A2A
searched not found
OpenTelemetry
OpenTelemetry — AgentCore Observability is OTel-based

Similar systems

Other agent ides & coding harnesses in the catalog, ranked by inbound references.

  • Claude Code (Anthropic) T1

    Anthropic's agentic coding tool: Claude as a coding agent in the terminal, IDEs (VS Code, JetBrains), desktop app, web/mobile, GitHub and Slack. Context via CLAUDE.md, skills, hooks, subagents and MCP servers.

  • Cursor (IDE) T1

    AI-first IDE that forked VS Code; Composer (multi-file edit) and Agent Mode (long-running coding agent) are its flagship surfaces. Memory layer = .cursorrules / Rules; recall via repo-aware Context Engine. Anysphere (parent) raised $900M Series C at $9.9B in May 2025; acquired by SpaceX (announced 2026-08-14, terms undisclosed), product continues under the Cursor brand.

  • OpenAI Codex CLI T1

    OpenAI's actively developed OSS terminal coding agent (Apr 2025), now written in Rust (codex-rs replaced the original TS CLI); also IDE extension + desktop app. Separate from the Codex Web cloud agent and the retired 2021 Codex model API. The codex mcp-server command (Codex as an MCP server) was deprecated on 2026-08-24 and removed in CLI 0.154.0 (2026-09-09); OpenAI points integrations to the experimental Codex app server, and codex mcp still connects Codex to external MCP servers.

  • Opencode (SST) T2

    SST team's open-source terminal coding agent — TypeScript, multi-model, MCP-native. Released 2025; explicitly positioned as a permissively-licensed Claude Code alternative. Memory via AGENTS.md (the emerging cross-harness convention).

  • GitHub Copilot (Agent Mode) T1

    The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.

  • Goose (Block) T2

    Block (Square)'s open-source on-machine agent — terminal + desktop GUI. Modular: extensions for shell, computer-control, MCP servers; multi-model via LiteLLM. Released 2024; positioned as a general-purpose local agent, not coding-only. Goose Recipes provide reusable agent workflows.

Sources (37 cited facts, 1 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • Pricing “Usage-based AWS pricing” → “Pay-per-use, no seat fee: Runtime from $0.0895/vCPU-hr + $0.00945/GB-hr; Gateway $0.005/1k calls; new AWS customers get up to $200 Free Tier credits” source
    • Deployment “Cloud (AWS-managed)” → “Managed-only — AWS-hosted (Runtime, Gateway, Memory, Identity, Browser, Code Interpreter, Observability)” source
    • MCP support first recorded as “yes — Gateway exposes APIs/Lambdas as MCP servers; Runtime hosts MCP-compatible tools; Agent Registry publishes MCP servers” source
    #258

Related systems

References (3)

  • Mem0 depends on at runtime — adjacent-infrastructure cell: AWS Bedrock; Mem0 (as memory provider); Strands Agents
  • OpenSearch depends on at runtime — backend-storage cell: AWS-managed (DynamoDB, S3, OpenSearch under the hood)
  • Strands Agents (AWS) integrates with — integrates with Strands Agents, Mem0 as memory provider.

Referenced by (18)

  • agentgateway integrates with — agentgateway standalone docs have a "Connect to AWS Bedrock AgentCore" agent-runtime routing page. (verified 2026-10-29)
  • Amazon Nova family depends on at runtime — adjacent-infrastructure cell: AWS Bedrock (distribution); Amazon Q Developer / Q Business; Alexa+; Trainium/Inferentia chips
  • Amazon Q Developer depends on at runtime — adjacent-infrastructure cell: AWS Bedrock; AWS IAM; CloudWatch
  • AWS Bedrock AgentCore Memory depends on at runtime — adjacent-infrastructure cell: requires AWS Bedrock + AgentCore
  • Fireworks AI integrates with — Fireworks AI docs integration: AWS AgentCore. (verified 2026-10-29)
  • Kiro depends on at runtime — adjacent-infrastructure cell: AWS Bedrock (model routing); Anthropic Claude + Amazon Nova
  • LangChain (framework) integrates with — LangChain docs have a Bedrock AgentCore Browser tool integration page. (verified 2026-10-29)
  • Langfuse integrates with — Langfuse's integrations directory has a Bedrock AgentCore (AWS) integration page. (verified 2026-10-29)
  • LiteLLM integrates with — LiteLLM docs have a Bedrock AgentCore provider page. (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — LlamaIndex has an official tool integration package llama-index-tools-aws-bedrock-agentcore in its repo. (verified 2026-10-29)
  • Mastra integrates with — Mastra repo ships the @mastra/agentcore workspace package (AWS Bedrock AgentCore Runtime sandbox provider). (verified 2026-10-29)
  • Meta Llama 4 family depends on at runtime — adjacent-infrastructure cell: HuggingFace Transformers; vLLM; llama.cpp; Together AI; Groq; AWS Bedrock; Azure AI Foundry
  • Mistral Large 2 / Mixtral family depends on at runtime — adjacent-infrastructure cell: Mistral Le Chat consumer (separate row); Codestral for code agents; Mistral Forge on-prem; AWS Bedrock / Azure AI distribution
  • Neo4j integrates with — Neo4j's GenAI ecosystem docs have a Bedrock AgentCore (AWS) integration page. (verified 2026-10-29)
  • Portkey AI integrates with — Portkey docs have an AWS AgentCore agent framework integration page. (verified 2026-10-29)
  • Strands Agents (AWS) integrates with — Strands Agents docs have a guide for deploying Strands agents to Amazon Bedrock AgentCore Runtime. (verified 2026-10-29)
  • Strands Agents Memory (AWS) depends on at runtime — adjacent-infrastructure cell: requires AWS; Bedrock + Mem0 / AgentCore Memory
  • Temporal integrates with — Temporal integrations catalog lists Serverless Workers on Amazon Bedrock AgentCore Runtime. (verified 2026-10-29)